MLM-Filter-13b Model Card
Model details
Model type: MLM-Filter-13b is an open-source MLLM trained to assess the data quality of image-text paired data. It can generate 4 quality metrics for image-text data: Image Text Matching, Object Detail Fulfillment, Caption Text Quality, and Semantic Understanding.
Model date: MLM-Filter-13B was trained in Dec 2023.
Paper or resources for more information: https://mlm-filter.github.io/
@article{wang2024finetuned,
title={Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters},
author={Wang, Weizhi and Mrini, Khalil and Yang, Linjie and Kumar, Sateesh and Tian, Yu and Yan, Xifeng and Wang, Heng},
journal={arXiv preprint arXiv:2403.02677},
year={2024}
}
License
Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved.
Where to send questions or comments about the model: https://github.com/Victorwz/MLM_Filter/issues
Intended use
Primary intended uses: MLM-Filter can be used as a drop-in replacement for CLIPScore in these tasks:
-
Score image-text data in large-scale pre-training dataset and then filter high-quality subsets based on the scores (For training MLLMs or VLMs, please consider to jointly use the Image-Text Matching score and the Object Detail Fulfillment score);
-
Evaluate the image-text alignment for image2text or text2image generation models;
-
Any potential applications with the need to calculate the image-text alignment.
Training dataset
- 46k instruction sampled from LLaVA-1.5 665k data.
- 4k instructions on image-text data quality assessment tasks ranging across 4 metrics.
Usage Sample
Please follow the instructions in https://github.com/Victorwz/MLM_Filter.